CSE 431 Computer Architecture Fall 2005 Lecture 04: Underst in addition to ing Per as long as mance Ma
Harris, Steve, Founder and Publisher has reference to this Academic Journal, PHwiki organized this Journal CSE 431 Computer Architecture Fall 2005 Lecture 04: Underst in addition to ing Per as long as mance Mary Jane Irwin ( www.cse.psu.edu/~mji ) www.cse.psu.edu/~cg431 [Adapted from Computer Organization in addition to Design, Patterson & Hennessy, © 2005, UCB] Indeed, the cost-per as long as mance ratio of the product will depend most heavily on the implementer, just as ease of use depends most heavily on the architect. The Mythical Man-Month, Brooks, pg 46 Per as long as mance Metrics Purchasing perspective given a collection of machines, which has the best per as long as mance least cost best cost/per as long as mance Design perspective faced with design options, which has the best per as long as mance improvement least cost best cost/per as long as mance Both require basis as long as comparison metric as long as evaluation Our goal is to underst in addition to what factors in the architecture contribute to overall system per as long as mance in addition to the relative importance ( in addition to cost) of these factors
This Particular University is Related to this Particular Journal
Defining (Speed) Per as long as mance Normally interested in reducing Response time (aka execution time) the time between the start in addition to the completion of a task Important to individual users Thus, to maximize per as long as mance, need to minimize execution time Throughput the total amount of work done in a given time Important to data center managers Decreasing response time almost always improves throughput per as long as manceX = 1 / execution-timeX If X is n times faster than Y, then Per as long as mance Factors Want to distinguish elapsed time in addition to the time spent on our task CPU execution time (CPU time) time the CPU spends working on a task Does not include time waiting as long as I/O or running other programs Can improve per as long as mance by reducing either the length of the clock cycle or the number of clock cycles required as long as a program or Review: Machine Clock Rate Clock rate (MHz, GHz) is inverse of clock cycle time (clock period) CC = 1 / CR one clock period 10 nsec clock cycle => 100 MHz clock rate 5 nsec clock cycle => 200 MHz clock rate 2 nsec clock cycle => 500 MHz clock rate 1 nsec clock cycle => 1 GHz clock rate 500 psec clock cycle => 2 GHz clock rate 250 psec clock cycle => 4 GHz clock rate 200 psec clock cycle => 5 GHz clock rate
Clock Cycles per Instruction Not all instructions take the same amount of time to execute One way to think about execution time is that it equals the number of instructions executed multiplied by the average time per instruction Clock cycles per instruction (CPI) the average number of clock cycles each instruction takes to execute A way to compare two different implementations of the same ISA Effective CPI Computing the overall effective CPI is done by looking at the different types of instructions in addition to their individual cycle counts in addition to averaging Overall effective CPI = (CPIi x ICi) i = 1 n Where ICi is the count (percentage) of the number of instructions of class i executed CPIi is the (average) number of clock cycles per instruction as long as that instruction class n is the number of instruction classes The overall effective CPI varies by instruction mix a measure of the dynamic frequency of instructions across one or many programs THE Per as long as mance Equation Our basic per as long as mance equation is then CPU time = Instruction-count x CPI x clock-cycle or These equations separate the three key factors that affect per as long as mance Can measure the CPU execution time by running the program The clock rate is usually given Can measure overall instruction count by using profilers/ simulators without knowing all of the implementation details CPI varies by instruction type in addition to ISA implementation as long as which we must know the implementation details
Determinates of CPU Per as long as mance CPU time = Instruction-count x CPI x clock-cycle Determinates of CPU Per as long as mance CPU time = Instruction-count x CPI x clock-cycle X X X X X X X X X X X X A Simple Example How much faster would the machine be if a better data cache reduced the average load time to 2 cycles How does this compare with using branch prediction to shave a cycle off the branch time What if two ALU instructions could be executed at once
A Simple Example How much faster would the machine be if a better data cache reduced the average load time to 2 cycles How does this compare with using branch prediction to shave a cycle off the branch time What if two ALU instructions could be executed at once .5 1.0 .3 .4 2.2 CPU time new = 1.6 x IC x CC so 2.2/1.6 means 37.5% faster 1.6 .5 .4 .3 .4 .5 1.0 .3 .2 2.0 CPU time new = 2.0 x IC x CC so 2.2/2.0 means 10% faster .25 1.0 .3 .4 1.95 CPU time new = 1.95 x IC x CC so 2.2/1.95 means 12.8% faster Comparing in addition to Summarizing Per as long as mance Guiding principle in reporting per as long as mance measurements is reproducibility list everything another experimenter would need to duplicate the experiment (version of the operating system, compiler settings, input set used, specific computer configuration (clock rate, cache sizes in addition to speed, memory size in addition to speed, etc.)) How do we summarize the per as long as mance as long as benchmark set with a single number The average of execution times that is directly proportional to total execution time is the arithmetic mean (AM) Where Timei is the execution time as long as the ith program of a total of n programs in the workload A smaller mean indicates a smaller average execution time in addition to thus improved per as long as mance SPEC Benchmarks www.spec.org
Example SPEC Ratings Other Per as long as mance Metrics Power consumption especially in the embedded market where battery life is important ( in addition to passive cooling) For power-limited applications, the most important metric is energy efficiency Summary: Evaluating ISAs Design-time metrics: Can it be implemented, in how long, at what cost Can it be programmed Ease of compilation Static Metrics: How many bytes does the program occupy in memory Dynamic Metrics: How many instructions are executed How many bytes does the processor fetch to execute the program How many clocks are required per instruction How “lean” a clock is practical Best Metric: Time to execute the program! depends on the instructions set, the processor organization, in addition to compilation techniques.
Next Lecture in addition to Reminders Next lecture MIPS non-pipelined datapath/control path review Reading assignment PH, Chapter 5 Reminders HW1 due September 13th Evening midterm exam scheduled Tuesday, October 18th , 20:15 to 22:15, Location 113 IST Please let me know via email ASAP if you have a conflict
Harris, Steve Founder and Publisher
Harris, Steve is from United States and they belong to Electronic Gaming Monthly and they are from San Francisco, United States got related to this Particular Journal. and Harris, Steve deal with the subjects like Consumer Audio; Consumer Electronics; New Products; Video/Computer Games
Journal Ratings by Georgia Military College-Warner Robins Campus
This Particular Journal got reviewed and rated by Georgia Military College-Warner Robins Campus and short form of this particular Institution is GA and gave this Journal an Excellent Rating.